© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15486
    Prev
    Next
    INDEX
    Explanations

    expressing possibility or speculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     These
    -2.33
    這些
    -2.14
     icona
    -2.02
    这些
    -1.95
    阋
    -1.93
    these
    -1.90
    鬭
    -1.88
     lancia
    -1.86
    infor
    -1.85
    ſchen
    -1.80
    POSITIVE LOGITS
     tradición
    1.58
     my
    1.55
     eficientes
    1.52
     excepcional
    1.46
     atractiva
    1.46
     fuerte
    1.46
     where
    1.46
     escuela
    1.45
    ͤ
    1.45
    -
    1.44
    Activations Density 0.022%

    No Known Activations